Search

Your search keyword '"Jiang, Hongxiang"' showing total 359 results
Start Over Author "Jiang, Hongxiang"
359 results on '"Jiang, Hongxiang"'

3. Multi-Camera Calibration Free BEV Representation for 3D Object Detection

Author

Jiang, Hongxiang, Meng, Wenming, Zhu, Hongmei, Zhang, Qian, and Yin, Jihao

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

In advanced paradigms of autonomous driving, learning Bird's Eye View (BEV) representation from surrounding views is crucial for multi-task framework. However, existing methods based on depth estimation or camera-driven attention are not stable to obtain transformation under noisy camera parameters, mainly with two challenges, accurate depth prediction and calibration. In this work, we present a completely Multi-Camera Calibration Free Transformer (CFT) for robust BEV representation, which focuses on exploring implicit mapping, not relied on camera intrinsics and extrinsics. To guide better feature learning from image views to BEV, CFT mines potential 3D information in BEV via our designed position-aware enhancement (PA). Instead of camera-driven point-wise or global transformation, for interaction within more effective region and lower computation cost, we propose a view-aware attention which also reduces redundant computation and promotes converge. CFT achieves 49.7% NDS on the nuScenes detection task leaderboard, which is the first work removing camera parameters, comparable to other geometry-guided methods. Without temporal input and other modal information, CFT achieves second highest performance with a smaller image input 1600 * 640. Thanks to view-attention variant, CFT reduces memory and transformer FLOPs for vanilla attention by about 12% and 60%, respectively, with improved NDS by 1.0%. Moreover, its natural robustness to noisy camera parameters makes CFT more competitive., Comment: 15 pages, 7 figures

Published
2022

11. Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion

Author

Jiang, Hongxiang, Yin, Jihao, Luo, Xiaoyan, and Wang, Fuxiang

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Abstract

Disentanglement learning aims to construct independent and interpretable latent variables in which generative models are a popular strategy. InfoGAN is a classic method via maximizing Mutual Information (MI) to obtain interpretable latent variables mapped to the target space. However, it did not emphasize independent characteristic. To explicitly infer latent variables with inter-independence, we propose a novel GAN-based disentanglement framework via embedding Orthogonal Basis Expansion (OBE) into InfoGAN network (Inference-InfoGAN) in an unsupervised way. Under the OBE module, one set of orthogonal basis can be adaptively found to expand arbitrary data with independence property. To ensure the target-wise interpretable representation, we add a consistence constraint between the expansion coefficients and latent variables on the base of MI maximization. Additionally, we design an alternating optimization step on the consistence constraint and orthogonal requirement updating, so that the training of Inference-InfoGAN can be more convenient. Finally, experiments validate that our proposed OBE module obtains adaptive orthogonal basis, which can express better independent characteristics than fixed basis expression of Discrete Cosine Transform (DCT). To depict the performance in downstream tasks, we compared with the state-of-the-art GAN-based and even VAE-based approaches on different datasets. Our Inference-InfoGAN achieves higher disentanglement score in terms of FactorVAE, Separated Attribute Predictability (SAP), Mutual Information Gap (MIG) and Variation Predictability (VP) metrics without model fine-tuning. All the experimental results illustrate that our method has inter-independence inference ability because of the OBE module, and provides a good trade-off between it and target-wise interpretability of latent variables via jointing the alternating optimization., Comment: 10 pages, 5 figures

Published
2021

35. Relationship between the flow regime characteristics and pressure signal in dense phase pneumatic conveying.

Author

Zhou, Jiawei, Yan, Xiangyu, Jiang, Hongxiang, Wang, Yingjia, Zheng, Zebing, and Wang, Qinghui

Subjects
PNEUMATIC-tube transportation, DISCRETE wavelet transforms, POWER spectra, SPECTRUM analysis, ADVECTION
Abstract

In the present study, a series of tests were conducted on a purpose-built experimental setup to investigate the relationship between the pressure signal and flow regime in horizontal pneumatic conveying processes. The pressure signals and images of the material flow regime during the conveying process were collected and analyzed. Direct observation, power spectrum analysis, and discrete wavelet transform were employed in this work. The results show that as the conveying pressure increases, the time taken to reach the steady conveying stage is shorter. A correlation was discovered among the frequency intervals, pneumatic conveying stages, and flow regimes. The periodicity of the decomposed signal increases with decomposition scale. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results